INDEX

Explanations

variables, mathematical symbols, and patterns in code or mathematical expressions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CanadaChoose

-0.51

 genoux

-0.48

 pleaſure

-0.48

 busiest

-0.47

bunt

-0.47

UrlResolution

-0.47

 purpoſe

-0.47

 atteinte

-0.46

 Garland

-0.45

ము

-0.42

POSITIVE LOGITS

 William

0.93

 Thomas

0.88

 utafitiHapana

0.88

 Joseph

0.87

William

0.87

 WILLIAM

0.87

Thomas

0.83

THOMAS

0.81

 James

0.81

Joseph

0.79

Activations Density 0.747%

variables, mathematical symbols, and patterns in code or mathematical expressions

No Comments

No Known Activations